Fast Flow-based Visuomotor Policies via Conditional Optimal Transport Couplings

TL;DR

This paper introduces a fast, flow-based visuomotor policy using conditional optimal transport couplings, significantly improving inference speed and success rates in robotic tasks while maintaining training complexity.

Contribution

It proposes a novel conditional optimal transport coupling method that accelerates flow-based policies for robot control, enabling real-time inference with high success rates.

Findings

Achieves 4% higher success rate than Diffusion Policy.

Provides 10x faster inference speed.

Generates high-quality, diverse actions in 1-2 steps.

Abstract

Diffusion and flow matching policies have recently demonstrated remarkable performance in robotic applications by accurately capturing multimodal robot trajectory distributions. However, their computationally expensive inference, due to the numerical integration of an ODE or SDE, limits their applicability as real-time controllers for robots. We introduce a methodology that utilizes conditional Optimal Transport couplings between noise and samples to enforce straight solutions in the flow ODE for robot action generation tasks. We show that naively coupling noise and samples fails in conditional tasks and propose incorporating condition variables into the coupling process to improve few-step performance. The proposed few-step policy achieves a 4% higher success rate with a 10x speed-up compared to Diffusion Policy on a diverse set of simulation tasks. Moreover, it produces high-quality and diverse action trajectories within 1-2 steps on a set of real-world robot tasks. Our method also retains the same training complexity as Diffusion Policy and vanilla Flow Matching, in contrast to distillation-based approaches.